Deep CNN jointing low-high level feature for image super-resolution

doi:10.1117/12.2524412

	Deep CNN jointing low-high level feature for image super-resolution
	Song, Xuhui 1; Liu, Weirong 1; Liu, Jie 3; Liu, Chaorong 2; Lu, Chunyan 1; Gao, Huiling 1
	2019
会议日期	December 12, 2018 - December 14, 2018
会议地点	Chengdu, China
关键词	Image reconstruction Neural networks Optical resolving power Semantics Textures Convolutional neural network High resolution image High-level semantic features Image super resolutions Low resolution images Low-high Perceptual effects Residual learning
卷号	11069
DOI	10.1117/12.2524412
英文摘要	Image super-resolution methods based on forward-feed convolutional neural networks (CNN) reconstruct the image with more details and sharper texture. However, most of these methods do not consider the influence of high level semantic feature to improve image perceptual effect. In this paper, we propose a deep CNN architecture jointing low-high level feature for image super-resolution. Our method uses 17 weight layers to predict residual between the high resolution and low resolution image. And we joint the low level and high level image features to constraint the network parameters updating. Experimental results validate that our method reconstruct the high resolution images with clear edge and less warp. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
会议录	Proceedings of SPIE - The International Society for Optical Engineering
会议录出版者	SPIE
语种	英语
ISSN号	0277786X
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/117950]
专题	电气工程与信息工程学院党委教师工作部（人事处、教师发展中心）
作者单位	1.College of Electrical and Information Engineering, Lanzhou University of Technology, China; 2.KEY Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, China 3.National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, China;
推荐引用方式 GB/T 7714	Song, Xuhui,Liu, Weirong,Liu, Jie,et al. Deep CNN jointing low-high level feature for image super-resolution[C]. 见:. Chengdu, China. December 12, 2018 - December 14, 2018.